Skip to content

armgit / letta

Public Imported from GitHub
0

Platform for stateful agents: AI with advanced memory that can learn and self-improve over time.

feat(core): increase Gemini timeout to 10 minutes (#9714)

Kevin Lina11ba9710ca0
diff --git a/conf.yaml b/conf.yaml
index b3b2eb82f..cbb160c83 100644
--- a/conf.yaml
+++ b/conf.yaml
@@ -260,6 +260,7 @@ model:
base_url: https://generativelanguage.googleapis.com/
force_minimum_thinking_budget: false
max_retries: 5
+ timeout_seconds: 600.0
# Google Vertex (-> GOOGLE_CLOUD_*)
# google_cloud:
diff --git a/letta/llm_api/google_ai_client.py b/letta/llm_api/google_ai_client.py
index f765a121e..c41d9b94b 100644
--- a/letta/llm_api/google_ai_client.py
+++ b/letta/llm_api/google_ai_client.py
@@ -9,7 +9,7 @@ from letta.llm_api.google_constants import GOOGLE_MODEL_FOR_API_KEY_CHECK
from letta.llm_api.google_vertex_client import GoogleVertexClient
from letta.log import get_logger
from letta.schemas.llm_config import LLMConfig
-from letta.settings import model_settings, settings
+from letta.settings import model_settings
logger = get_logger(__name__)
@@ -18,7 +18,7 @@ class GoogleAIClient(GoogleVertexClient):
provider_label = "Google AI"
def _get_client(self, llm_config: Optional[LLMConfig] = None):
- timeout_ms = int(settings.llm_request_timeout_seconds * 1000)
+ timeout_ms = int(model_settings.gemini_timeout_seconds * 1000)
api_key = None
if llm_config:
api_key, _, _ = self.get_byok_overrides(llm_config)
@@ -30,7 +30,7 @@ class GoogleAIClient(GoogleVertexClient):
)
async def _get_client_async(self, llm_config: Optional[LLMConfig] = None):
- timeout_ms = int(settings.llm_request_timeout_seconds * 1000)
+ timeout_ms = int(model_settings.gemini_timeout_seconds * 1000)
api_key = None
if llm_config:
api_key, _, _ = await self.get_byok_overrides_async(llm_config)
diff --git a/letta/settings.py b/letta/settings.py
index 3f2360995..aa316385f 100644
--- a/letta/settings.py
+++ b/letta/settings.py
@@ -204,6 +204,7 @@ class ModelSettings(BaseSettings):
gemini_base_url: str = "https://generativelanguage.googleapis.com/"
gemini_force_minimum_thinking_budget: bool = False
gemini_max_retries: int = 5
+ gemini_timeout_seconds: float = 600.0
# google vertex
google_cloud_project: Optional[str] = None